Tabriz University of Medical Sciences Medical Journal of Tabriz University of Medical Sciences 2783-2031 42 6 2021 02 24 The noise reduction of medical radiography images using fractional moments 649 658 10.34172/mj.2021.005 EN Mahdieh Gholizadeh https://orcid.org/0000-0001-5759-9841 Mohammad Hossein Gholizadeh https://orcid.org/0000-0003-4337-5067 Hossein Ghayoumi Zadeh https://orcid.org/0000-0002-5390-3938 Mostafa Danaeian https://orcid.org/0000-0001-8527-8172 Journal Article 10.34172/mj.2021.005 2019 02 28 Background: This paper presents a method to improve medical radiography images based on the use of statistical signal moments. Methods: In this paper, the image with noise is considered as a statistical signal, and the noise reduction is performed by using fractional moments. The fractional moment’s method, on the one hand, has a speed similar to the moment method, and, on the other hand, has not the limitations of the moment method, which sometimes achieves inaccurate results. The proposed method is ultimately examined on radiographic images (CT). Results: The information obtained from the fractional moments of the received signal is a criterion to estimate the noise parameters and the gray scales of the main image. One of the limitations of the proposed method is that the image should be sent several times, because in statistical discussions, we cannot make a decision with only one sample. The error of the proposed noise reduction method in terms of the number of times the original image was sent, is about 0.009, 0.0009, 0.0002, and 0.0001, for n = 3, n = 6, n = 9 and n = 14, respectively. Conclusion: The simulation results show that the proposed method is more effective than the most conventional noise reduction methods, both in the low signal to noise ratio and in terms of image quality, and is more powerful than the most notable noise removal methods in restoring the subtleties and image details.